Glad you liked the first result. And ugh, sorry you hit that error on the second go. You're right, that "unexpected error" message is pretty useless. Better error handling is at the top of my to-do list now.
That's a great question. Right now, the inference costs are coming out of my own pocket. My main goal was to let people experience the model's potential without any barriers.
To keep the project sustainable in the long run, I'm exploring some options, like potentially offering a paid tier for heavy users or more advanced features. For now, I'm focused on improving the core experience and will do my best to keep costs low so it remains accessible to as many people as possible.
I'm so sorry you ran into that, and thank you for reporting it. This is exactly the kind of feedback I need at this early stage.
You're right, my backend logs show that most requests are succeeding, which means there must be an error happening somewhere between the front-end and the server that I'm not catching properly yet.
Based on this, implementing a more robust error logging system is now my top priority. I'll get on it right away so I can find and fix these issues for everyone. Thanks again for giving it a try.
Thanks! Not yet. To get this launched quickly and validate the idea, I'm currently using a cloud API to handle the inference.
However, my plan is to eventually deploy the model on my own server. I'll be sure to document the entire process—from setup to optimization—and share it as a detailed guide on the site for anyone interested!
I'm really sorry that you had such an experience. I took a close look at the website you mentioned (https://minimator.app), and it's indeed a beautiful and fun tool. In comparison, my website does seem quite rough, especially when there are so many alternatives out there that offer similar functionality but with much better design.
Being labeled as 'AI spam' was never my intention. I genuinely hope that the product I created can actually help users because I myself have found a lot of joy in the process of AI-generated art. I want to make something better to help others, but unfortunately, my current starting point seems quite poor.
Thank you for your feedback, and once again, I apologize for the negative experience. I'll start by working on the design suggestions you provided to make my product better, more unique, and more valuable.